Annotation of documentViewer/documentViewer.py, revision 1.138
1.18 dwinter 1:
1.1 dwinter 2: from OFS.Folder import Folder
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22 dwinter 4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
1.1 dwinter 5: from AccessControl import ClassSecurityInfo
1.8 casties 6: from AccessControl import getSecurityManager
1.1 dwinter 7: from Globals import package_home
1.119 abukhman 8: from Products.zogiLib.zogiLib import browserCheck
1.1 dwinter 9:
1.70 casties 10: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.73 casties 11: import Ft.Xml.Domlette
1.1 dwinter 12: import os.path
1.7 casties 13: import sys
1.1 dwinter 14: import urllib
1.138 ! abukhman 15:
1.70 casties 16: import urllib2
1.20 dwinter 17: import logging
1.28 casties 18: import math
1.18 dwinter 19: import urlparse
1.70 casties 20: import cStringIO
1.99 dwinter 21: import re
1.43 casties 22:
1.117 abukhman 23:
1.22 dwinter 24: def logger(txt,method,txt2):
25: """logging"""
26: logging.info(txt+ txt2)
27:
28:
1.4 casties 29: def getInt(number, default=0):
30: """returns always an int (0 in case of problems)"""
31: try:
32: return int(number)
33: except:
1.29 casties 34: return int(default)
1.4 casties 35:
1.1 dwinter 36: def getTextFromNode(nodename):
1.18 dwinter 37: """get the cdata content of a node"""
1.8 casties 38: if nodename is None:
39: return ""
1.1 dwinter 40: nodelist=nodename.childNodes
41: rc = ""
42: for node in nodelist:
43: if node.nodeType == node.TEXT_NODE:
44: rc = rc + node.data
45: return rc
46:
1.43 casties 47: def serializeNode(node, encoding='utf-8'):
48: """returns a string containing node as XML"""
49: buf = cStringIO.StringIO()
1.75 casties 50: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 51: s = buf.getvalue()
52: buf.close()
53: return s
54:
1.118 abukhman 55: def getBrowserType(self):
56: """get browser type object"""
57: if self.REQUEST.SESSION.has_key('browserType'):
58: return self.REQUEST.SESSION['browserType']
59: else:
60: bt = browserCheck(self)
61: self.REQUEST.SESSION.set('browserType', bt)
62: logging.debug("documentViewer (BROWSER TYPE) bt %s"%bt)
63: return bt
64:
65:
1.9 casties 66: def getParentDir(path):
67: """returns pathname shortened by one"""
68: return '/'.join(path.split('/')[0:-1])
69:
70:
1.70 casties 71: def getHttpData(url, data=None, num_tries=3, timeout=10):
72: """returns result from url+data HTTP request"""
73: # we do GET (by appending data to url)
74: if isinstance(data, str) or isinstance(data, unicode):
75: # if data is string then append
76: url = "%s?%s"%(url,data)
77: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
78: # urlencode
79: url = "%s?%s"%(url,urllib.urlencode(data))
80:
81: response = None
82: errmsg = None
83: for cnt in range(num_tries):
84: try:
1.95 abukhman 85: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 86: if sys.version_info < (2, 6):
87: # set timeout on socket -- ugly :-(
88: import socket
89: socket.setdefaulttimeout(float(timeout))
90: response = urllib2.urlopen(url)
91: else:
92: response = urllib2.urlopen(url,timeout=float(timeout))
93: # check result?
94: break
95: except urllib2.HTTPError, e:
1.95 abukhman 96: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 97: errmsg = str(e)
98: # stop trying
99: break
100: except urllib2.URLError, e:
1.95 abukhman 101: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 102: errmsg = str(e)
103: # stop trying
104: #break
105:
106: if response is not None:
107: data = response.read()
108: response.close()
109: return data
110:
111: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
112: #return None
1.1 dwinter 113:
114:
115:
1.3 casties 116: ##
117: ## documentViewer class
118: ##
119: class documentViewer(Folder):
1.1 dwinter 120: """document viewer"""
121: meta_type="Document viewer"
122:
123: security=ClassSecurityInfo()
1.3 casties 124: manage_options=Folder.manage_options+(
1.1 dwinter 125: {'label':'main config','action':'changeDocumentViewerForm'},
126: )
127:
1.3 casties 128: # templates and forms
129: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 130: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
131: toc_text = PageTemplateFile('zpt/toc_text', globals())
132: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 133: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
134: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 135: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 136: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 137: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 138: head_main = PageTemplateFile('zpt/head_main', globals())
139: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 140: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 141:
142:
1.32 dwinter 143: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 144: security.declareProtected('View management screens','changeDocumentViewerForm')
145: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
146:
1.1 dwinter 147:
1.45 abukhman 148: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 149: """init document viewer"""
150: self.id=id
151: self.title=title
1.4 casties 152: self.thumbcols = thumbcols
153: self.thumbrows = thumbrows
1.8 casties 154: # authgroups is list of authorized groups (delimited by ,)
155: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 156: # create template folder so we can always use template.something
157:
158: templateFolder = Folder('template')
159: #self['template'] = templateFolder # Zope-2.12 style
160: self._setObject('template',templateFolder) # old style
161: try:
1.70 casties 162: import MpdlXmlTextServer
1.71 casties 163: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 164: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 165: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 166: except Exception, e:
1.70 casties 167: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 168: try:
169: from Products.zogiLib.zogiLib import zogiLib
170: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
171: #templateFolder['zogilib'] = zogilib
172: templateFolder._setObject('zogilib',zogilib)
173: except Exception, e:
174: logging.error("Unable to create zogiLib for zogilib: "+str(e))
175:
1.70 casties 176:
177: # proxy text server methods to fulltextclient
178: def getTextPage(self, **args):
179: """get page"""
180: return self.template.fulltextclient.getTextPage(**args)
181:
182: def getQuery(self, **args):
183: """get query"""
184: return self.template.fulltextclient.getQuery(**args)
185:
186: def getSearch(self, **args):
187: """get search"""
188: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 189:
190: def getGisPlaces(self, **args):
1.121 abukhman 191: """get gis places"""
1.120 abukhman 192: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 193:
194: def getAllGisPlaces(self, **args):
1.122 abukhman 195: """get all gis places """
196: return self.template.fulltextclient.getAllGisPlaces(**args)
197:
198: def getOrigPages(self, **args):
199: """get original page number """
200: return self.template.fulltextclient.getOrigPages(**args)
201:
1.72 casties 202: def getNumPages(self, docinfo):
1.70 casties 203: """get numpages"""
1.72 casties 204: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 205:
206: def getNumTextPages(self, docinfo):
207: """get numpages text"""
208: return self.template.fulltextclient.getNumTextPages(docinfo)
209:
1.70 casties 210: def getTranslate(self, **args):
211: """get translate"""
212: return self.template.fulltextclient.getTranslate(**args)
213:
214: def getLemma(self, **args):
215: """get lemma"""
216: return self.template.fulltextclient.getLemma(**args)
217:
218: def getToc(self, **args):
219: """get toc"""
220: return self.template.fulltextclient.getToc(**args)
221:
222: def getTocPage(self, **args):
223: """get tocpage"""
224: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 225:
1.70 casties 226:
1.32 dwinter 227: security.declareProtected('View','thumbs_rss')
228: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
229: '''
230: view it
231: @param mode: defines how to access the document behind url
232: @param url: url which contains display information
233: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
234:
235: '''
1.95 abukhman 236: logging.debug("HHHHHHHHHHHHHH:load the rss")
237: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 238:
239: if not hasattr(self, 'template'):
240: # create template folder if it doesn't exist
241: self.manage_addFolder('template')
242:
243: if not self.digilibBaseUrl:
244: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
245:
246: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 247: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 ! abukhman 248: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 249: ''' ZDES '''
1.32 dwinter 250: pt = getattr(self.template, 'thumbs_main_rss')
251:
252: if viewMode=="auto": # automodus gewaehlt
1.70 casties 253: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 254: viewMode="text"
255: else:
256: viewMode="images"
257:
258: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
259:
1.3 casties 260: security.declareProtected('View','index_html')
1.138 ! abukhman 261: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
1.3 casties 262: '''
263: view it
1.26 casties 264: @param mode: defines how to access the document behind url
1.3 casties 265: @param url: url which contains display information
1.44 casties 266: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 267: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 268: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 269: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 270: '''
271:
1.138 ! abukhman 272: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 273:
1.3 casties 274: if not hasattr(self, 'template'):
1.43 casties 275: # this won't work
276: logging.error("template folder missing!")
277: return "ERROR: template folder missing!"
1.3 casties 278:
1.43 casties 279: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 280: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 281:
1.4 casties 282: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 283:
1.44 casties 284: if tocMode != "thumbs":
285: # get table of contents
286: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 287:
1.21 dwinter 288: if viewMode=="auto": # automodus gewaehlt
1.71 casties 289: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 290: viewMode="text_dict"
1.21 dwinter 291: else:
292: viewMode="images"
1.44 casties 293:
1.138 ! abukhman 294: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 295:
1.44 casties 296: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 297: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 298:
1.36 dwinter 299: def generateMarks(self,mk):
300: ret=""
1.44 casties 301: if mk is None:
302: return ""
1.73 casties 303: if not isinstance(mk, list):
1.71 casties 304: mk=[mk]
1.36 dwinter 305: for m in mk:
1.37 dwinter 306: ret+="mk=%s"%m
1.36 dwinter 307: return ret
1.43 casties 308:
1.44 casties 309:
1.43 casties 310: def findDigilibUrl(self):
311: """try to get the digilib URL from zogilib"""
312: url = self.template.zogilib.getDLBaseUrl()
313: return url
1.67 casties 314:
315: def getDocumentViewerURL(self):
316: """returns the URL of this instance"""
317: return self.absolute_url()
1.43 casties 318:
319: def getStyle(self, idx, selected, style=""):
320: """returns a string with the given style and append 'sel' if path == selected."""
321: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
322: if idx == selected:
323: return style + 'sel'
324: else:
325: return style
1.36 dwinter 326:
1.4 casties 327: def getLink(self,param=None,val=None):
328: """link to documentviewer with parameter param set to val"""
1.9 casties 329: params=self.REQUEST.form.copy()
1.4 casties 330: if param is not None:
1.7 casties 331: if val is None:
332: if params.has_key(param):
333: del params[param]
1.4 casties 334: else:
1.9 casties 335: params[param] = str(val)
1.43 casties 336:
337: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 338: params["mode"] = "imagepath"
339: params["url"] = getParentDir(params["url"])
1.7 casties 340:
1.9 casties 341: # quote values and assemble into query string
1.74 casties 342: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
343: ps = urllib.urlencode(params)
1.9 casties 344: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 345: return url
346:
1.32 dwinter 347: def getLinkAmp(self,param=None,val=None):
348: """link to documentviewer with parameter param set to val"""
349: params=self.REQUEST.form.copy()
350: if param is not None:
351: if val is None:
352: if params.has_key(param):
353: del params[param]
354: else:
355: params[param] = str(val)
356:
357: # quote values and assemble into query string
1.95 abukhman 358: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 359: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
360: url=self.REQUEST['URL1']+"?"+ps
361: return url
1.40 casties 362:
1.26 casties 363: def getInfo_xml(self,url,mode):
364: """returns info about the document as XML"""
365:
366: if not self.digilibBaseUrl:
367: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
368:
369: docinfo = self.getDocinfo(mode=mode,url=url)
370: pt = getattr(self.template, 'info_xml')
371: return pt(docinfo=docinfo)
372:
1.4 casties 373:
1.9 casties 374: def isAccessible(self, docinfo):
1.8 casties 375: """returns if access to the resource is granted"""
376: access = docinfo.get('accessType', None)
1.95 abukhman 377: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 378: if access is not None and access == 'free':
1.95 abukhman 379: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 380: return True
1.17 casties 381: elif access is None or access in self.authgroups:
1.9 casties 382: # only local access -- only logged in users
383: user = getSecurityManager().getUser()
1.95 abukhman 384: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 385: if user is not None:
386: #print "user: ", user
387: return (user.getUserName() != "Anonymous User")
388: else:
389: return False
1.8 casties 390:
1.95 abukhman 391: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 392: return False
1.9 casties 393:
1.8 casties 394:
1.35 dwinter 395: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 396: """gibt param von dlInfo aus"""
1.7 casties 397: if docinfo is None:
398: docinfo = {}
1.35 dwinter 399:
400: for x in range(cut):
1.38 dwinter 401:
1.35 dwinter 402: path=getParentDir(path)
1.38 dwinter 403:
1.13 casties 404: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 405:
1.95 abukhman 406: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 407:
1.70 casties 408: txt = getHttpData(infoUrl)
409: if txt is None:
1.13 casties 410: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 411:
412: dom = Parse(txt)
1.10 casties 413: sizes=dom.xpath("//dir/size")
1.95 abukhman 414: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 415:
1.10 casties 416: if sizes:
417: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 418: else:
419: docinfo['numPages'] = 0
1.43 casties 420:
421: # TODO: produce and keep list of image names and numbers
1.7 casties 422:
423: return docinfo
1.8 casties 424:
1.99 dwinter 425: def getIndexMetaPath(self,url):
426: """gib nur den Pfad zurueck"""
427: regexp = re.compile(r".*(experimental|permanent)/(.*)")
428: regpath = regexp.match(url)
429: if (regpath==None):
430: return ""
1.110 abukhman 431: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 432: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
433:
1.111 abukhman 434:
435:
1.99 dwinter 436: def getIndexMetaUrl(self,url):
437: """returns utr of index.meta document at url"""
438:
1.12 casties 439: metaUrl = None
1.9 casties 440: if url.startswith("http://"):
441: # real URL
1.12 casties 442: metaUrl = url
1.9 casties 443: else:
444: # online path
445: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 446: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 447: if not metaUrl.endswith("index.meta"):
448: metaUrl += "/index.meta"
1.99 dwinter 449:
450: return metaUrl
451:
452: def getDomFromIndexMeta(self, url):
453: """get dom from index meta"""
454: dom = None
455: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 456:
1.99 dwinter 457: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 458: txt=getHttpData(metaUrl)
459: if txt is None:
1.12 casties 460: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 461:
462: dom = Parse(txt)
1.9 casties 463: return dom
1.20 dwinter 464:
465: def getPresentationInfoXML(self, url):
466: """returns dom of info.xml document at url"""
467: dom = None
468: metaUrl = None
469: if url.startswith("http://"):
470: # real URL
471: metaUrl = url
472: else:
473: # online path
474: server=self.digilibBaseUrl+"/servlet/Texter?fn="
475: metaUrl=server+url.replace("/mpiwg/online","")
476:
1.70 casties 477: txt=getHttpData(metaUrl)
478: if txt is None:
1.20 dwinter 479: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 480:
481: dom = Parse(txt)
1.20 dwinter 482: return dom
1.9 casties 483:
484:
1.33 dwinter 485: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 486: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 487: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 488:
489: access = None
490:
491: if docinfo is None:
492: docinfo = {}
493:
494: if dom is None:
1.38 dwinter 495: for x in range(cut):
1.33 dwinter 496: path=getParentDir(path)
1.99 dwinter 497: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 498:
1.8 casties 499: acctype = dom.xpath("//access-conditions/access/@type")
500: if acctype and (len(acctype)>0):
501: access=acctype[0].value
1.9 casties 502: if access in ['group', 'institution']:
1.8 casties 503: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
504:
505: docinfo['accessType'] = access
506: return docinfo
1.6 casties 507:
1.8 casties 508:
1.33 dwinter 509: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 510: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 511: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 512:
1.3 casties 513: if docinfo is None:
514: docinfo = {}
1.38 dwinter 515:
1.3 casties 516: if dom is None:
1.38 dwinter 517: for x in range(cut):
1.33 dwinter 518: path=getParentDir(path)
1.99 dwinter 519: dom = self.getDomFromIndexMeta(path)
520:
521: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 522:
1.95 abukhman 523: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 524: # put in all raw bib fields as dict "bib"
525: bib = dom.xpath("//bib/*")
526: if bib and len(bib)>0:
527: bibinfo = {}
528: for e in bib:
529: bibinfo[e.localName] = getTextFromNode(e)
530: docinfo['bib'] = bibinfo
531:
532: # extract some fields (author, title, year) according to their mapping
1.4 casties 533: metaData=self.metadata.main.meta.bib
534: bibtype=dom.xpath("//bib/@type")
535: if bibtype and (len(bibtype)>0):
536: bibtype=bibtype[0].value
1.2 dwinter 537: else:
1.4 casties 538: bibtype="generic"
1.27 casties 539:
1.4 casties 540: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 541: docinfo['bib_type'] = bibtype
1.4 casties 542: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 543: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
544: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 545: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 546: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 547: try:
548: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
549: except: pass
550: try:
551: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
552: except: pass
553: try:
554: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
555: except: pass
1.95 abukhman 556: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 557: try:
558: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
559: except:
560: docinfo['lang']=''
1.113 abukhman 561:
1.3 casties 562: return docinfo
1.42 abukhman 563:
1.104 abukhman 564:
565: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
566: """gets name info from the index.meta file at path or given by dom"""
567: if docinfo is None:
568: docinfo = {}
569:
570: if dom is None:
571: for x in range(cut):
572: path=getParentDir(path)
573: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 574:
1.115 abukhman 575: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 576: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 577: return docinfo
1.42 abukhman 578:
1.43 casties 579: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
580: """parse texttool tag in index meta"""
1.95 abukhman 581: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 582: if docinfo is None:
583: docinfo = {}
584: if docinfo.get('lang', None) is None:
585: docinfo['lang'] = '' # default keine Sprache gesetzt
586: if dom is None:
1.99 dwinter 587: dom = self.getDomFromIndexMeta(url)
1.43 casties 588:
589: archivePath = None
590: archiveName = None
591:
592: archiveNames = dom.xpath("//resource/name")
593: if archiveNames and (len(archiveNames) > 0):
594: archiveName = getTextFromNode(archiveNames[0])
595: else:
1.70 casties 596: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 597:
598: archivePaths = dom.xpath("//resource/archive-path")
599: if archivePaths and (len(archivePaths) > 0):
600: archivePath = getTextFromNode(archivePaths[0])
601: # clean up archive path
602: if archivePath[0] != '/':
603: archivePath = '/' + archivePath
604: if archiveName and (not archivePath.endswith(archiveName)):
605: archivePath += "/" + archiveName
606: else:
607: # try to get archive-path from url
1.95 abukhman 608: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 609: if (not url.startswith('http')):
610: archivePath = url.replace('index.meta', '')
611:
612: if archivePath is None:
613: # we balk without archive-path
614: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
615:
616: imageDirs = dom.xpath("//texttool/image")
617: if imageDirs and (len(imageDirs) > 0):
618: imageDir = getTextFromNode(imageDirs[0])
619:
620: else:
621: # we balk with no image tag / not necessary anymore because textmode is now standard
622: #raise IOError("No text-tool info in %s"%(url))
623: imageDir = ""
624: #xquery="//pb"
625: docinfo['imagePath'] = "" # keine Bilder
626: docinfo['imageURL'] = ""
627:
628: if imageDir and archivePath:
629: #print "image: ", imageDir, " archivepath: ", archivePath
630: imageDir = os.path.join(archivePath, imageDir)
631: imageDir = imageDir.replace("/mpiwg/online", '')
632: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
633: docinfo['imagePath'] = imageDir
634:
635: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
636:
637: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
638: if viewerUrls and (len(viewerUrls) > 0):
639: viewerUrl = getTextFromNode(viewerUrls[0])
640: docinfo['viewerURL'] = viewerUrl
1.70 casties 641:
642: # old style text URL
1.43 casties 643: textUrls = dom.xpath("//texttool/text")
644: if textUrls and (len(textUrls) > 0):
645: textUrl = getTextFromNode(textUrls[0])
646: if urlparse.urlparse(textUrl)[0] == "": #keine url
647: textUrl = os.path.join(archivePath, textUrl)
648: # fix URLs starting with /mpiwg/online
649: if textUrl.startswith("/mpiwg/online"):
650: textUrl = textUrl.replace("/mpiwg/online", '', 1)
651:
652: docinfo['textURL'] = textUrl
653:
1.70 casties 654: # new style text-url-path
1.43 casties 655: textUrls = dom.xpath("//texttool/text-url-path")
656: if textUrls and (len(textUrls) > 0):
657: textUrl = getTextFromNode(textUrls[0])
1.51 casties 658: docinfo['textURLPath'] = textUrl
659: if not docinfo['imagePath']:
660: # text-only, no page images
1.103 abukhman 661: docinfo = self.getNumTextPages(docinfo)
1.43 casties 662:
663: presentationUrls = dom.xpath("//texttool/presentation")
664: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 665: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.137 abukhman 666: docinfo =self.getOrigPages(docinfo=docinfo)
1.43 casties 667:
668: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
669: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
670: # durch den relativen Pfad auf die presentation infos
671: presentationPath = getTextFromNode(presentationUrls[0])
672: if url.endswith("index.meta"):
673: presentationUrl = url.replace('index.meta', presentationPath)
674: else:
675: presentationUrl = url + "/" + presentationPath
1.51 casties 676:
1.43 casties 677: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
678:
679: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 680:
1.43 casties 681: return docinfo
1.3 casties 682:
1.20 dwinter 683:
684: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
685: """gets the bibliographical information from the preseantion entry in texttools
686: """
687: dom=self.getPresentationInfoXML(url)
1.29 casties 688: try:
689: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
690: except:
691: pass
692: try:
693: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
694: except:
695: pass
696: try:
697: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
698: except:
699: pass
1.20 dwinter 700: return docinfo
701:
1.33 dwinter 702: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 703: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 704: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 705: if docinfo is None:
706: docinfo = {}
1.6 casties 707: path=path.replace("/mpiwg/online","")
1.3 casties 708: docinfo['imagePath'] = path
1.35 dwinter 709: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 710:
1.39 dwinter 711: pathorig=path
1.38 dwinter 712: for x in range(cut):
713: path=getParentDir(path)
1.95 abukhman 714: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 715: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 716: docinfo['imageURL'] = imageUrl
717:
1.39 dwinter 718: #path ist the path to the images it assumes that the index.meta file is one level higher.
719: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
720: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 721: return docinfo
722:
1.2 dwinter 723:
1.3 casties 724: def getDocinfo(self, mode, url):
725: """returns docinfo depending on mode"""
1.95 abukhman 726: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 727: # look for cached docinfo in session
1.21 dwinter 728: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 729: docinfo = self.REQUEST.SESSION['docinfo']
730: # check if its still current
731: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 732: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 733: return docinfo
734: # new docinfo
735: docinfo = {'mode': mode, 'url': url}
736: if mode=="texttool": #index.meta with texttool information
737: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
738: elif mode=="imagepath":
739: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 740: elif mode=="filepath":
1.37 dwinter 741: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 742: else:
1.95 abukhman 743: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 744: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 745:
1.95 abukhman 746: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.135 abukhman 747:
1.3 casties 748: self.REQUEST.SESSION['docinfo'] = docinfo
749: return docinfo
1.69 abukhman 750:
1.138 ! abukhman 751: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization="",originalPage=None):
1.3 casties 752: """returns pageinfo with the given parameters"""
753: pageinfo = {}
1.4 casties 754: current = getInt(current)
1.132 abukhman 755:
756: pageinfo ['originalPage'] = originalPage
1.4 casties 757: pageinfo['current'] = current
758: rows = int(rows or self.thumbrows)
759: pageinfo['rows'] = rows
760: cols = int(cols or self.thumbcols)
761: pageinfo['cols'] = cols
762: grpsize = cols * rows
763: pageinfo['groupsize'] = grpsize
1.28 casties 764: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
765: # int(current / grpsize) * grpsize +1))
1.3 casties 766: pageinfo['start'] = start
1.4 casties 767: pageinfo['end'] = start + grpsize
1.44 casties 768: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 769: np = int(docinfo['numPages'])
770: pageinfo['end'] = min(pageinfo['end'], np)
771: pageinfo['numgroups'] = int(np / grpsize)
772: if np % grpsize > 0:
1.69 abukhman 773: pageinfo['numgroups'] += 1
1.44 casties 774: pageinfo['viewMode'] = viewMode
775: pageinfo['tocMode'] = tocMode
1.98 abukhman 776: #pageinfo['characterNormalization'] =characterNormalization
777: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
1.45 abukhman 778: pageinfo['query'] = self.REQUEST.get('query',' ')
779: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
780: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 781: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 782: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 783: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 784: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 785: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 786: toc = int (pageinfo['tocPN'])
787: pageinfo['textPages'] =int (toc)
1.90 abukhman 788:
1.135 abukhman 789: logging.debug("originalPage: %s"%originalPage)
1.123 abukhman 790:
1.48 abukhman 791: if 'tocSize_%s'%tocMode in docinfo:
792: tocSize = int(docinfo['tocSize_%s'%tocMode])
793: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 794: # cached toc
1.48 abukhman 795: if tocSize%tocPageSize>0:
796: tocPages=tocSize/tocPageSize+1
797: else:
798: tocPages=tocSize/tocPageSize
1.69 abukhman 799: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 800: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 801: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 802: return pageinfo
803:
1.69 abukhman 804: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 805: """init document viewer"""
806: self.title=title
807: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 808: self.thumbrows = thumbrows
809: self.thumbcols = thumbcols
1.8 casties 810: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 811: if RESPONSE is not None:
812: RESPONSE.redirect('manage_main')
1.1 dwinter 813:
814: def manage_AddDocumentViewerForm(self):
815: """add the viewer form"""
1.3 casties 816: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 817: return pt()
818:
1.43 casties 819: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 820: """add the viewer"""
1.43 casties 821: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 822: self._setObject(id,newObj)
823:
824: if RESPONSE is not None:
825: RESPONSE.redirect('manage_main')
1.3 casties 826:
827: ## DocumentViewerTemplate class
828: class DocumentViewerTemplate(ZopePageTemplate):
829: """Template for document viewer"""
830: meta_type="DocumentViewer Template"
831:
832:
833: def manage_addDocumentViewerTemplateForm(self):
834: """Form for adding"""
835: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
836: return pt()
837:
838: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
839: REQUEST=None, submit=None):
840: "Add a Page Template with optional file content."
841:
842: self._setObject(id, DocumentViewerTemplate(id))
843: ob = getattr(self, id)
1.23 dwinter 844: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 845: logging.info("txt %s:"%txt)
1.23 dwinter 846: ob.pt_edit(txt,"text/html")
1.3 casties 847: if title:
848: ob.pt_setTitle(title)
849: try:
850: u = self.DestinationURL()
851: except AttributeError:
852: u = REQUEST['URL1']
853:
854: u = "%s/%s" % (u, urllib.quote(id))
855: REQUEST.RESPONSE.redirect(u+'/manage_main')
856: return ''
857:
858:
1.14 casties 859:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to documentViewer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer